Find contradicting decisions

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the bar is lower. The description adds valuable context beyond the annotation by explaining that the tool is a heuristic that only surfaces candidates for review and does not adjudicate disagreements—this tells the agent the output is advisory, not authoritative, which is critical for downstream use. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler. The core function is front-loaded in the first sentence, and the second sentence adds a crucial caveat about its heuristic nature. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is moderately complex (compares cross-conversation decisions) but has no output schema and no explanation of parameters. The description does not define 'recent conversations,' does not clarify what the threshold represents, and omits any mention of the output format (e.g., pairs with confidence scores). With only the readOnlyHint annotation and this sparse description, an agent would struggle to set parameters meaningfully or interpret results confidently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for the two parameters, and the description provides zero explanation of what 'limit' or 'threshold' mean. The schema only gives numeric ranges/defaults but no semantic meaning—an agent cannot infer that threshold likely refers to a disagreement confidence level or how limit caps pairs returned. The description fails to compensate for this gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Compares'), a clear resource ('decisions across recent conversations'), and the output ('reports pairs that appear to disagree'). It also distinguishes itself from find_duplicates by focusing on disagreements rather than similar items, making its purpose unambiguous even without inspecting schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for initial conflict review by noting it 'surfaces candidates for review, it does not adjudicate them,' but it never explicitly states when to choose this over sibling tools like analyze_conversation or find_duplicates, nor does it mention any exclusions. The heuristic nature is clear, but the guidance is indirect rather than prescriptive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.